Related papers: Soft-labeling Strategies for Rapid Sub-Typing

Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms. Previous efforts tend to mitigate this problem via…

This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target…

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…

Instance segmentation of unknown objects from images is regarded as relevant for several robot skills including grasping, tracking and object sorting. Recent results in computer vision have shown that large hand-labeled datasets enable high…

Creating large, good quality labeled data has become one of the major bottlenecks for developing machine learning applications. Multiple techniques have been developed to either decrease the dependence of labeled data (zero/few-shot…

In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational performances. Such data are challenging to obtain as it…

The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data. It is challenging mainly due to two aspects: (1) it lacks good feature representation of novel classes; (2) a few of…

This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…

Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples. Existing approaches search globally for the optimal examples to label, scaling linearly or even…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Despite the success of deep learning methods in medical image segmentation tasks, the human-level performance relies on massive training data with high-quality annotations, which are expensive and time-consuming to collect. The fact is that…

Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an effective way…

Recent advances in appearance-based models have shown improved eye tracking performance in difficult scenarios like occlusion due to eyelashes, eyelids or camera placement, and environmental reflections on the cornea and glasses. The key…

Automatic image cropping models predict reframing boxes to enhance image aesthetics. Yet, the scarcity of labeled data hinders the progress of this task. To overcome this limitation, we explore the possibility of utilizing both labeled and…

In this paper, we study the use of soft labels to train a system for sound event detection (SED). Soft labels can result from annotations which account for human uncertainty about categories, or emerge as a natural representation of…

Learning-based image reconstruction models, such as those based on the U-Net, require a large set of labeled images if good generalization is to be guaranteed. In some imaging domains, however, labeled data with pixel- or voxel-level label…

Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…

The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded…

Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from…

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…